@inproceedings{robertson-goldwater-2018-evaluating,
    title = "Evaluating Historical Text Normalization Systems: How Well Do They Generalize?",
    author = "Robertson, Alexander  and
      Goldwater, Sharon",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N18-2113/",
    doi = "10.18653/v1/N18-2113",
    pages = "720--725",
    abstract = {We highlight several issues in the evaluation of historical text normalization systems that make it hard to tell how well these systems would actually work in practice{---}i.e., for new datasets or languages; in comparison to more na{\"i}ve systems; or as a preprocessing step for downstream NLP tools. We illustrate these issues and exemplify our proposed evaluation practices by comparing two neural models against a na{\"i}ve baseline system. We show that the neural models generalize well to unseen words in tests on five languages; nevertheless, they provide no clear benefit over the na{\"i}ve baseline for downstream POS tagging of an English historical collection. We conclude that future work should include more rigorous evaluation, including both intrinsic and extrinsic measures where possible.}
}